Title :
Structure Evaluation of Receptive Field Layer in TAM Network
Author :
Hayashi, Isao ; Maeda, Toshiyuki
Author_Institution :
Kansai Univ., Osaka
Abstract :
TAM (topographic attentive mapping) network is a biologically-motivated neural network with receptive fields of Gabor function. However, the receptive field´s layer is monotype, and there is a lack of performance for rotating visual images. In this paper, we formulate four TAM networks with multilayer structure of extensive receptive fields. We discuss their performance and show the usefulness of TAM network using some examples of character recognition.
Keywords :
neural nets; optical character recognition; Gabor function; TAM network; character recognition; neural network; receptive field layer; structure evaluation; topographic attentive mapping; visual image; Cells (biology); Character recognition; Cybernetics; Detectors; Filtering; Humans; Multi-layer neural network; Neural networks; Retina; Visual system;
Conference_Titel :
Systems, Man and Cybernetics, 2006. SMC '06. IEEE International Conference on
Conference_Location :
Taipei
Print_ISBN :
1-4244-0099-6
Electronic_ISBN :
1-4244-0100-3
DOI :
10.1109/ICSMC.2006.384936
